# Puppeteer (MCP Server)

> Archived reference server for Puppeteer browser automation

- Type: MCP server
- Publisher: Model Context Protocol (official)
- Categories: Development
- Website: https://github.com/modelcontextprotocol/servers-archived/tree/main/src/puppeteer
- Source: https://github.com/modelcontextprotocol/servers-archived
- Transport: stdio
- Launch command: npx -y @modelcontextprotocol/server-puppeteer
- Sign-in: none
- Environment variables: PUPPETEER_LAUNCH_OPTIONS
- Listed: 2024-11-25

## About

Archived reference MCP server (moved to modelcontextprotocol/servers-archived and no longer maintained) for browser automation with Puppeteer. Supports navigation, screenshots, clicking, form filling and JavaScript evaluation; consider Playwright MCP or Chrome DevTools MCP instead.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add puppeteer --env PUPPETEER_LAUNCH_OPTIONS=YOUR_PUPPETEER_LAUNCH_OPTIONS -- npx -y @modelcontextprotocol/server-puppeteer
   ```

   config.toml:

   ```toml
   [mcp_servers.puppeteer]
   command = "npx"
   args = ["-y", "@modelcontextprotocol/server-puppeteer"]
   
   [mcp_servers.puppeteer.env]
   PUPPETEER_LAUNCH_OPTIONS = "YOUR_PUPPETEER_LAUNCH_OPTIONS"
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Puppeteer",
       params={"command": "npx", "args": ["-y", "@modelcontextprotocol/server-puppeteer"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Navigate to example.com and take a screenshot")
       print(result.final_output)
   ```

## Tools

- `puppeteer_navigate`
- `puppeteer_screenshot`
- `puppeteer_click`
- `puppeteer_hover`
- `puppeteer_fill`
- `puppeteer_select`
- `puppeteer_evaluate`

## Example prompts

- "Navigate to example.com and take a screenshot"
- "Fill in the search box and click submit"
- "Run document.title in the page"

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/puppeteer · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.